寻找同源词：斯拉夫历史音系学中的连续和离散语言嵌入
In search of isoglosses: continuous and discrete language embeddings in Slavic historical phonology
摘要：
本文研究了神经网络架构在多语言环境中有效学习历时语音概括的能力。我们使用三种不同类型的语言嵌入（密集，sigmoid和直通）。我们发现，直通模型优于其他两个方面的准确性，但Sigmoid模型的语言嵌入显示出最强的协议与传统的斯拉夫语言的子分组。我们发现，直通模型已经学会了连贯的，半可解释的声音变化的信息，并为未来的研究勾勒出方向。
英文摘要：
This paper investigates the ability of neural network architectures to effectively learn diachronic phonological generalizations in a multilingual setting. We employ models using three different types of language embedding (dense, sigmoid, and straight-through). We find that the Straight-Through model outperforms the other two in terms of accuracy, but the Sigmoid model's language embeddings show the strongest agreement with the traditional subgrouping of the Slavic languages. We find that the Straight-Through model has learned coherent, semi-interpretable information about sound change, and outline directions for future research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
